Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[NPM-3751] retry network ID fetch #33330

Merged
merged 8 commits into from
Feb 6, 2025
Merged

[NPM-3751] retry network ID fetch #33330

Show file tree
Hide file tree
Changes from 3 commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
b57da6b
retry network ID fetch
akarpz Jan 23, 2025
d05d125
retry fetching networkID in various checks
akarpz Jan 27, 2025
dd9c2c6
Merge branch 'main' into akarpowich/retry_network_id
akarpz Jan 27, 2025
8f1e6e2
only retry during startup
akarpz Jan 30, 2025
feb52b1
docstrings and log levels
akarpz Jan 30, 2025
fba0947
log error if all retries fail
akarpz Jan 30, 2025
773075a
Merge branch 'main' into akarpowich/retry_network_id
akarpz Feb 3, 2025
f261f2b
retry based on attempt
akarpz Feb 3, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion cmd/system-probe/modules/network_tracer.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -115,7 +115,7 @@ func (nt *networkTracer) Register(httpMux *module.Router) error {
httpMux.HandleFunc("/network_id", utils.WithConcurrencyLimit(utils.DefaultMaxConcurrentRequests, func(w http.ResponseWriter, req *http.Request) {
id, err := nt.tracer.GetNetworkID(req.Context())
if err != nil {
log.Errorf("unable to retrieve network_id: %s", err)
log.Errorf("unable to retrieve network ID: %s", err)
w.WriteHeader(500)
return
}
Expand Down
8 changes: 8 additions & 0 deletions pkg/process/checks/container.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -111,6 +111,14 @@ func (c *ContainerCheck) Run(nextGroupID func() int32, options *RunOptions) (Run
defer c.Unlock()
startTime := time.Now()

if c.networkID == "" {
networkID, err := retryGetNetworkID(c.sysprobeClient)
if err != nil {
log.Warnf("error getting network ID: %s", err)
}
c.networkID = networkID
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

maybe check that networkID is not empty, if the function retryGetNetworkID is erroring than the value for networkID will be ""

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I ended up changing the logic around a bit

}

var err error
var containers []*model.Container
var lastRates map[string]*proccontainers.ContainerRateMetrics
Expand Down
8 changes: 8 additions & 0 deletions pkg/process/checks/net.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -161,6 +161,14 @@ func (c *ConnectionsCheck) ShouldSaveLastRun() bool { return false }
func (c *ConnectionsCheck) Run(nextGroupID func() int32, _ *RunOptions) (RunResult, error) {
start := time.Now()

if c.networkID == "" {
networkID, err := retryGetNetworkID(c.sysprobeClient)
if err != nil {
log.Warnf("error getting network ID: %s", err)
}
c.networkID = networkID
}

conns, err := c.getConnections()
if err != nil {
return nil, err
Expand Down
8 changes: 8 additions & 0 deletions pkg/process/checks/process.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -390,6 +390,14 @@ func procsToStats(procs map[int32]*procutil.Process) map[int32]*procutil.Stats {

// Run collects process data (regular metadata + stats) and/or realtime process data (stats only)
func (p *ProcessCheck) Run(nextGroupID func() int32, options *RunOptions) (RunResult, error) {
if p.networkID == "" {
networkID, err := retryGetNetworkID(p.sysprobeClient)
if err != nil {
log.Warnf("error getting network ID: %s", err)
}
p.networkID = networkID
}

if options == nil {
return p.run(nextGroupID(), false)
}
Expand Down
2 changes: 1 addition & 1 deletion pkg/process/net/common.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -80,7 +80,7 @@ func GetNetworkID(client *http.Client) (string, error) {
defer resp.Body.Close()

if resp.StatusCode != http.StatusOK {
return "", fmt.Errorf("network_id request failed: url: %s, status code: %d", req.URL, resp.StatusCode)
return "", fmt.Errorf("network ID request failed: url: %s, status code: %d", req.URL, resp.StatusCode)
}

body, err := sysprobeclient.ReadAllResponseBody(resp)
Expand Down
Loading